Top-1 Accuracy: 73.3Top-5 Accuracy: 94.0Parameters: 87GFLOPs: 180x6
Papers with Code · CC BY-SA 4.0
Activity Recognition
Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.
<span class="description-source">Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters </span>
논문
Top-1 Accuracy: 70.9Top-5 Accuracy: 92.5
Top-1 Accuracy: 73.8Top-5 Accuracy: 94.4Parameters: 311GFLOPs: 131x6
Top-1 Accuracy: 73.7Top-5 Accuracy: 94.0Parameters: 87GFLOPs: 180x6
Top-1 Accuracy: 73.3Top-5 Accuracy: 94.1Parameters: 213.1
Top-1 Accuracy: 73.6
Top-1 Accuracy: 74.3Top-5 Accuracy: 94.6Parameters: 305GFLOPs: 597x6
Top-1 Accuracy: 71.4Top-5 Accuracy: -Parameters: 89GFLOPs: 321x3
Top-1 Accuracy: 71.6
Top-1 Accuracy: 70.2Top-5 Accuracy: 91.8
Top-1 Accuracy: 71.5
Top-1 Accuracy: 70.1Top-5 Accuracy: 92.8Parameters: 68.5GFLOPs: 197x3
Top-1 Accuracy: 71.4Top-5 Accuracy: 93.5
Top-1 Accuracy: 69.8
Top-1 Accuracy: 72.3Top-5 Accuracy: 93.9GFLOPs: 8248
Top-1 Accuracy: 69.8
Top-1 Accuracy: 69.6Top-5 Accuracy: 92.2GFLOPs: 198x3
Top-1 Accuracy: 73.4Top-5 Accuracy: 93.8
Top-1 Accuracy: 71.2Top-5 Accuracy: 92.8Parameters: 50.1GFLOPs: 259x3
Top-1 Accuracy: 73.0Top-5 Accuracy: 94.5GFLOPs: 5154
Top-1 Accuracy: 73.7
Top-1 Accuracy: 69.6Top-5 Accuracy: 92.7Parameters: 89GFLOPs: 321x3
Top-1 Accuracy: 72.2Top-5 Accuracy: 93.0